Edgar Lobaton

Publications

• Planning Curvature-Constrained Paths to Multiple Goals Using Disk Sampling

  E. Lobaton, J. Zhang, S. Patil, R. Alterovitz

  IEEE International Conference on Robotics and Automation, Shanghai, China; 01/2011

  We present a new path planning method for robots with curvature constraints on their motion to visit multiple goals in any order. We first introduce a disk-based roadmap that facilitates computation of curvature-constrained paths that optimize an application specific metric. This roadmap, which gene... [more] We present a new path planning method for robots with curvature constraints on their motion to visit multiple goals in any order. We first introduce a disk-based roadmap that facilitates computation of curvature-constrained paths that optimize an application specific metric. This roadmap, which generalizes to both 2D and 3D workspaces, is constructed by sampling disks of bounded curvature and generating feasible transitions between these sampled disks. We then formulate the path planning problem to multiple goals as a Steiner directed tree problem over this roadmap. Since optimally solving the multi-goal planning problem requires exponential time, we propose greedy heuristics to efficiently compute a path that visits multiple goals. We apply the planner in the context of medical needle steering where the needle tip must reach multiple goals in soft tissue, a common requirement for clinical procedures such as biopsies, drug delivery, and brachytherapy cancer treatment. We demonstrate that the proposed heuristics converge to within 5% of optimal and that considering the multi-goal planning problem significantly decreases tissue that must be cut compared to sequential execution of single goal plans.

• A Methodology for Remote Virtual Interaction in Teleimmersive Environments

  R. Vasudevan, E. Lobaton, G. Kurillo, R. Bajcsy, T. Bernardin, B. Hamann, K. Nahrstedt

  ACM Multimedia Systems Conference, Scottsdale, Arizona; 02/2010

  Though the quality of imaging devices, the accuracy of algorithms that construct 3D data, and the hardware available to render such data have all improved, the algorithms available to calibrate, reconstruct, and then visualize such data are difficult to use, extremely noise sensitive, and unreasonably... [more] Though the quality of imaging devices, the accuracy of algorithms that construct 3D data, and the hardware available to render such data have all improved, the algorithms available to calibrate, reconstruct, and then visualize such data are difficult to use, extremely noise sensitive, and unreasonably slow. In this paper, we describe a multi-camera system that creates a highly accurate (on the order of a centimeter), 3D reconstruction of an environment in real time (under 30 ms) that allows for remote interaction between users. The paper addresses the aforementioned deficiencies by featuring an overview of the technology and algorithms used to calibrate, reconstruct, and render objects in the system. The algorithm produces partial 3D meshes, instead of dense point clouds, which are combined on the renderer to create a unified model of the environment. The chosen representation of the data allows for high compression ratios for transfer to remote sites. We demonstrate the accuracy and speed of our results on a variety of benchmarks and data collected from our own system.

• Local Occlusion Detection Under Deformations Using Topological Invariants

  E. Lobaton, R. Vasudevan, R. Bajcsy, R. Alterovitz

  European Conference on Computer Vision (ECCV), Greece; 01/2010

  Occlusions provide critical cues about the 3D structure of man-made and natural scenes. We present a mathematical framework and algorithm to detect and localize occlusions in image sequences of scenes that include deforming objects. Our occlusion detector works under far weaker assumptions than othe... [more] Occlusions provide critical cues about the 3D structure of man-made and natural scenes. We present a mathematical framework and algorithm to detect and localize occlusions in image sequences of scenes that include deforming objects. Our occlusion detector works under far weaker assumptions than other detectors. We prove that occlusions in deforming scenes occur when certain well-defined local topological invariants are not preserved. Our framework employs these invariants to detect occlusions with a zero false positive rate under assumptions of bounded deformations and color variation. The novelty and strength of this methodology is that it does not rely on spatio-temporal derivatives or matching, which can be problematic in scenes including deforming objects, but is instead based on a mathematical representation of the underlying cause of occlusions in a deforming 3D scene. We demonstrate the effectiveness of the occlusion detector using image sequences of natural scenes, including deforming cloth and hand motions.

• A Framework for High Quality Visualization of Geographically Distributed 3D Teleimmersive Applications

  R. Vasudevan, G. Kurillo, E. Lobaton, T. Bernardin, O. Kreylos, R. Bajcsy, K. Nahrstedt

  IEEE Transactions on Multimedia. 01/2010;

• A Distributed Topological Camera Network Representation for Tracking Applications

  E. Lobaton, R. Vasudevan, R. Bajcsy, S. Sastry

  IEEE Transactions on Image Processing. 01/2010; 19:2516 - 2529.

  Sensor networks have been widely used for surveillance, monitoring, and tracking. Camera networks, in particular, provide a large amount of information that has traditionally been processed in a centralized manner employing a priori knowledge of camera location and of the physical layout of the envi... [more] Sensor networks have been widely used for surveillance, monitoring, and tracking. Camera networks, in particular, provide a large amount of information that has traditionally been processed in a centralized manner employing a priori knowledge of camera location and of the physical layout of the environment. Unfortunately, these conventional requirements are far too demanding for ad-hoc distributed networks. In this article, we present a simplicial representation of a camera network called the camera network complex ( $CN$-complex), that accurately captures topological information about the visual coverage of the network. This representation provides a coordinate-free calibration of the sensor network and demands no localization of the cameras or objects in the environment. A distributed, robust algorithm, validated via two experimental setups, is presented for the construction of the representation using only binary detection information. We demonstrate the utility of this representation in capturing holes in the coverage, performing tracking of agents, and identifying homotopic paths.

• Real-Time Stereo-Vision System for 3D Teleimmersive Collaboration

  R. Vasudevan, Z. Zhou, G. Kurillo, E. Lobaton, R. Bajcsy, K. Nahrstedt

  IEEE Conference on Multimedia & Expo (ICME), Singapore; 01/2010

  Though the variety of desktop real time stereo vision systems has grown considerably in the past several years, few make any verifiable claims about the accuracy of the algorithms used to construct 3D data or describe how the data generated by such systems, which is large in size, can be effectively... [more] Though the variety of desktop real time stereo vision systems has grown considerably in the past several years, few make any verifiable claims about the accuracy of the algorithms used to construct 3D data or describe how the data generated by such systems, which is large in size, can be effectively distributed. In this paper, we describe a system that creates an accurate (on the order of a centimeter), 3D reconstruction of an environment in real time (under 30 ms) that also allows for remote interaction between users. This paper addresses how to reconstruct, compress, and visualize the 3D environment. In contrast to most commercial desktop real time stereo vision systems our algorithm produces 3D meshes instead of dense point clouds, which we show allows for better quality visualizations. The chosen representation of the data also allows for high compression ratios for transfer to remote sites. We demonstrate the accuracy and speed of our results on a variety of benchmarks.

• A Low-Bandwidth Camera Sensor Platform with Applications in Smart Camera Networks

  P. Chen, K. Hong, N. Naikal, S.S. Sastry, D. Tygar, P. Yan, A.Y. Yang, L.-C. Chang, L. Lin, S. Wang, E. Lobaton, S. Oh, P. Ahammad

  ACM Transactions on Sensor Networks (TOSN). 01/2010;

• Robust Construction of the Camera Network Complex for Topology Recovery

  E J Lobaton, R Vasudevan, S S Sastry, R Bajcsy

  International Conference on Distributed Smart Cameras (ICDSC), Como, Italy; 09/2009

  While performing tasks such as estimating the topology of camera network coverage or coordinate-free object tracking and navigation, knowledge of camera position and other geometric constraints about the environment are considered unnecessary. Instead, topological information captured by the constru... [more] While performing tasks such as estimating the topology of camera network coverage or coordinate-free object tracking and navigation, knowledge of camera position and other geometric constraints about the environment are considered unnecessary. Instead, topological information captured by the construction of a simplicial representation called the $CN$-Complex can be utilized to perform these tasks. This representation can be thought of as a generalization of the so-called vision graph of a camera network. The construction of this simplicial complex consists of two steps: the decomposition of the camera coverage through the detection of occlusion events, and the discovery of overlapping areas between the multiple decomposed regions. In this paper, we present an algorithm for performing both of these tasks in the presence of multiple targets and noisy observations. The algorithm exploits temporal correlations of the detections to estimate probabilities of overlap in a distributed manner. No correspondence, appearance models, or tracking are utilized. Instead of applying a single threshold on the probabilities, we analyze the persistence of the topological features in our representation through a filtration process. We demonstrate the validity of our approach through simulation and an experimental setup.

• Occlusions in Camera Networks and Vision: The Bridge between Topological Recovery and Metric Reconstruction

  E J Lobaton

  05/2009

  Degree: Ph.D.

  Supervisor: S Shankar Sastry

• Building an Algebraic Topological Model of Wireless Camera Networks

  E J Lobaton, P Ahammad, S S Sastry

  05/2009: pages 95-115;

  ISBN: 978-0-12-374633-7

• Algebraic approach to recovering topological information in distributed camera networks

  E J Lobaton, P Ahammad, S S Sastry

  Information Processing in Sensor Networks (IPSN), San Francisco, CA; 04/2009

  Camera networks are widely used for tasks such as surveillance, monitoring and tracking. In order to accomplish these tasks, knowledge of localization information such as camera locations and other geometric constraints about the environment (e.g. walls, rooms, and building layout) are typically con... [more] Camera networks are widely used for tasks such as surveillance, monitoring and tracking. In order to accomplish these tasks, knowledge of localization information such as camera locations and other geometric constraints about the environment (e.g. walls, rooms, and building layout) are typically considered to be essential. However, this information is not required for tasks such as estimating the topology of camera network coverage, or coordinate-free object tracking and navigation. In this paper, we propose a simplicial representation (called CN-Complex) that can be constructed from discrete local observations, and utilize this novel representation to recover topological information of the network coverage. We prove that our representation captures the correct topological information for coverage in 2.5D layouts, and demonstrate its utility in simulations as well as an experimental setup. Our proposed approach is particularly useful in the context of ad-hoc camera networks in indoor/outdoor urban environments with distributed but limited computational power and energy.

• Modeling and Optimization of a Single-Flagellum Micro-Structure

  E J Lobaton, A Bayen

  IEEE Transactions on Control Systems Technology. 01/2009; 17:907-916.

  Bacteria such as Rhodobacter sphaeroides use a single flagellum for propulsion and change of orientation. These types of simple organisms have inspired microrobotic designs with potential applications in medicine, which motivates this work. In this paper, an elastic model for a single-flagellum micr... [more] Bacteria such as Rhodobacter sphaeroides use a single flagellum for propulsion and change of orientation. These types of simple organisms have inspired microrobotic designs with potential applications in medicine, which motivates this work. In this paper, an elastic model for a single-flagellum micro-structure is presented and followed by an analysis of the system based on optimization. The model is based on the method of Regularized Stokeslets which allows for a discretization of the system into particles connected by spring forces. The optimization analysis leads to the design of an optimal elasticity distribution that maximizes the mean forward speed of the structure. These elasticity coefficients are obtained through the use of adjoint-based optimization. The results are illustrated through simulations showing improvement on the swimming pattern of the micro-structure.

• A Framework for Collaborative Real-Time 3D Teleimmersion in a Geographically Distributed Environment

  G Kurillo, R Vasudevan, E J Lobaton, R Bajcsy

  International Symposyum on Multimedia (ISM), Berkeley, CA; 12/2008

  In this paper, we present a framework for immersive 3D video conferencing and geographically distributed collaboration. Our multi-camera system performs a full-body 3D reconstruction of users in real time and renders their image in a virtual space allowing remote interaction between users and the vi... [more] In this paper, we present a framework for immersive 3D video conferencing and geographically distributed collaboration. Our multi-camera system performs a full-body 3D reconstruction of users in real time and renders their image in a virtual space allowing remote interaction between users and the virtual environment. The paper features an overview of the technology and algorithms used for calibration, capturing, and reconstruction. We introduce stereo mapping using adaptive triangulation which allows for fast (under 25 ms) and robust real-time 3D reconstruction. The chosen representation of the data provides high compression ratios for transfer to a remote site. The algorithm produces partial 3D meshes, instead of dense point clouds, which are combined on the renderer to create a unified model of the user. We have successfully demonstrated the use of our system in various applications such as remote dancing and immersive Tai Chi learning.

• CITRIC: A low-bandwidth wireless camera network platform

  o P. Chen, P. Ahammad, C. Boyer, S.I. Huang, L. Lin, E.J. Lobaton, M. Meingast, S. Oh, S. Wang, P. Yan, A.Y. Yang, C. Yeo, L.C. Chang, D. Tygar, S.S. Sastry

  International Conference on Distributed Smart Cameras (ICDSC), Stanford, CA; 09/2008

  In this paper, we propose and demonstrate a novel wireless camera network system, called CITRIC. The core component of this system is a new hardware platform that integrates a camera, a frequency-scalable (up to 624 MHz) CPU, 16MB FLASH, and 64MB RAM onto a single device. The device then connects wi... [more] In this paper, we propose and demonstrate a novel wireless camera network system, called CITRIC. The core component of this system is a new hardware platform that integrates a camera, a frequency-scalable (up to 624 MHz) CPU, 16MB FLASH, and 64MB RAM onto a single device. The device then connects with a standard sensor network mote to form a camera mote. The design enables in-network processing of images to reduce communication requirements, which has traditionally been high in existing camera networks with centralized processing. We also propose a back-end client/server architecture to provide a user interface to the system and support further centralized processing for higher-level applications. Our camera mote enables a wider variety of distributed pattern recognition applications than traditional platforms because it provides more computing power and tighter integration of physical components while still consuming relatively little power. Furthermore, the mote easily integrates with existing low-bandwidth sensor networks because it can communicate over the IEEE 802.15.4 protocol with other sensor network platforms. We demonstrate our system on three applications: image compression, target tracking, and camera localization.
• 3.90

  Impact points

  Nanonails: a simple geometrical approach to electrically tunable superlyophobic surfaces.

  A Ahuja, J A Taylor, V Lifton, A A Sidorenko, T R Salamon, E J Lobaton, P Kolodner, T N Krupenkin

  Langmuir : the ACS journal of surfaces and colloids. 02/2008; 24(1):9-14.

  In this work, dynamically tunable, superlyophobic surfaces capable of undergoing a transition from profound superlyophobic behavior to almost complete wetting have been demonstrated for the first time. In the initial state, with no voltage applied, these surfaces exhibit contact angles as high as 15... [more] In this work, dynamically tunable, superlyophobic surfaces capable of undergoing a transition from profound superlyophobic behavior to almost complete wetting have been demonstrated for the first time. In the initial state, with no voltage applied, these surfaces exhibit contact angles as high as 150 degrees for a wide variety of liquids with surface tensions ranging from 21.8 mN/m (ethanol) to 72.0 mN/m (water). Upon application of an electrical voltage, a transition from the superlyophobic state to wetting is observed. We have examined experimentally and theoretically the nature of these transitions. The reported results provide novel methods of manipulating liquids on the microscale.
• 3.02

  Impact points

  Computation of constant mean curvature surfaces: Application to the gas-liquid interface of a pressurized fluid on a superhydrophobic surface.

  E J Lobaton, T R Salamon

  Journal of colloid and interface science. 11/2007; 314(1):184-98.

  The interface shape separating a gas layer within a superhydrophobic surface consisting of a square lattice of posts from a pressurized liquid above the surface is computed numerically. The interface shape is described by a constant mean curvature surface that satisfies the Young-Laplace equation wi... [more] The interface shape separating a gas layer within a superhydrophobic surface consisting of a square lattice of posts from a pressurized liquid above the surface is computed numerically. The interface shape is described by a constant mean curvature surface that satisfies the Young-Laplace equation with the three-phase gas-liquid-solid contact line assumed pinned at the post outer edge. The numerical method predicts the existence of constant mean curvature solutions from the planar, zero curvature solution up to a maximum curvature that is dependent on the post shape, size and pitch. An overall force balance between surface tension and pressure forces acting on the interface yields predictions for the maximum curvature that agree with the numerical simulations to within one percent for convex shapes such as circular and square posts, but significantly over predicts the maximum curvature for non-convex shapes such as a circular post with a sinusoidal surface perturbation. Changing the post shape to increase the contact line length, while maintaining constant post area, results in increases of 2 to 12% in the maximum computable curvature for contact line length increases of 11 to 77%. Comparisons are made to several experimental studies for interface shape and pressure stability.

  Download

• Modeling and Optimization Analysis of Single Flagellum Bacterial Motion

  E J Lobaton, A Bayen

  American Control Conference (ACC), New York, NY; 07/2007

  Bacteria such as Rhodobacter sphaeroides use a single flagellum for propulsion and change of orientation. Simple organisms such as this have inspired nanorobotic designs with potential applications in medicine which motivates the present work. In this article, an elastic model for a single flagellum... [more] Bacteria such as Rhodobacter sphaeroides use a single flagellum for propulsion and change of orientation. Simple organisms such as this have inspired nanorobotic designs with potential applications in medicine which motivates the present work. In this article, an elastic model for a single flagellum bacterium is presented and followed by an analysis of the system based on optimization. The model is based on the method of Regularized Stokeslet which allows for a discretization of the system into particles which are connected by spring forces. An optimal elasticity distribution that maximizes the mean forward speed is obtained. These elasticity coefficients are obtained through the use of an adjoint-based optimization scheme. The results are illustrated through a simulation showing improvement on the swimming patter of the bacteria.
• 1.87

  Impact points

  A study of bacterial flagellar bundling.

  Heather Flores, Edgar Lobaton, Stefan Méndez-Diez, Svetlana Tlupova, Ricardo Cortez

  Bulletin of mathematical biology. 02/2005; 67(1):137-68.

  Certain bacteria, such as Escherichia coli (E. coli) and Salmonella typhimurium (S. typhimurium), use multiple flagella often concentrated at one end of their bodies to induce locomotion. Each flagellum is formed in a left-handed helix and has a motor at the base that rotates the flagellum in a cork... [more] Certain bacteria, such as Escherichia coli (E. coli) and Salmonella typhimurium (S. typhimurium), use multiple flagella often concentrated at one end of their bodies to induce locomotion. Each flagellum is formed in a left-handed helix and has a motor at the base that rotates the flagellum in a corkscrew motion. We present a computational model of the flagellar motion and their hydrodynamic interaction. The model is based on the equations of Stokes flow to describe the fluid motion. The elasticity of the flagella is modeled with a network of elastic springs while the motor is represented by a torque at the base of each flagellum. The fluid velocity due to the forces is described by regularized Stokeslets and the velocity due to the torques by the associated regularized rotlets. Their expressions are derived. The model is used to analyze the swimming motion of a single flagellum and of a group of three flagella in close proximity to one another. When all flagellar motors rotate counterclockwise, the hydrodynamic interaction can lead to bundling. We present an analysis of the flow surrounding the flagella. When at least one of the motors changes its direction of rotation, the same initial conditions lead to a tumbling behavior characterized by the separation of the flagella, changes in their orientation, and no net swimming motion. The analysis of the flow provides some intuition for these processes.

  Download